Photo by CJ Dayrit on Unsplash

It’s incorrect to treat either emotions or consciousness like an axiom in the formulation of general intelligence.

I agree that emotions are a parameter in cognition. But this parameter is also regulated by cognition. How we perceive the world is regulated by our cognition and emotions are an emergent response to our perception. An axiom is a boundary condition.

Emotions are affected by our perception and thus it’s not a boundary condition but rather is a constraint that morphs with our subsequent interactions with our world and our minds.

Others treat consciousness as an axiom in the framing of the…


Photo by Alex Iby on Unsplash

All cognition involves the interpretation of language. But what is the difference between the brain’s interpretation of its senses and the interpretation of language?

For starters, the interpretation of language should appear to be simpler because another agent who vocalized or wrote the expressions did so with an intention of conveying meaning. Language is conditioned so the interpreter can understand it.

However, our environment doesn’t condition its expression for an agent to understand it. Here is the interesting observation, it is the agent itself that conditions how it interprets its senses.

A living thing interprets its environment by virtue of…


VQGAN + CLIP Generated using ‘General Intelligence and the Evolution of Language’ as seed.

The consequence of humans trading in nouns is that they spend an inordinate amount of effort attempting to understand the design of natural things without understanding why that thing emerged.

We focus too much on the forest but always overlook the trees. Our reductionist habits are biased towards simplicity. We achieve simplicity by removing context from the equation.

This is despite our natural human ability to involve context to unearth meaning.

Physics is extremely successful at employing reductionist methods to understand our world. Physics has invented compact universal laws that describe the inexorable rules of reality.

But we must understand…


When we first learned how to drive on the highway, it was a conscious process. Now it’s unconscious and we can daydream for miles without even being conscious of the road. Habit becomes unconscious that’s how the brain works.

That means that everybody’s conscious habits are going to be different. So the nature of one’s consciousness differs from person to person because we have developed different thinking habits.

Some people always have vocalizations in their head, others do not. Some people can vividly visualize scenes, other’s can’t. We build up all kinds of unconscious habits that shape our thinking.

Conscious…


Roadmap by VQGAN & CLIP

Three years ago I proposed a deep learning capability maturity model (see: A New Capability Maturity Model for Deep Learning ). Today I will revisit this maturity model (i.e. a roadmap in more pedestrian terms) to see it in light of my more developed understanding of general intelligence.

Let’s begin with the premise that “reasoning and learning are two sides of the same coin and should be treated equivalently.” This notion can be illustrated in this diagram:


Hierarchy and Tragedy by VQGAN &CLIP

200,000 years or 10,000 human generations is what it took to get where we are today. It took 9,700 generations of humans to realize the value of the scientific method. Stupidity is doing the same thing over and over again without making progress. So what were 9,700 generations of humans doing when they were not doing science?

These generations spent all their time constructing models of reality that were influenced more by authority than by a systematic method of model construction that challenged authority. …


Photo by Elena Mozhvilo on Unsplash

It is patently absurd that so many researchers in cognitive science believe in a magical local rule (i.e. Hebbian learning, gradient descent, free energy, neural circuitry, etc) that leads to complex intelligence. I guess humans just never get tired of their reductionist methods.

But yet we have made tremendous strides using just local rules like gradient descent and massive computation to emulate intuition found in human minds.

Deep learning methods appear like a bottom-up process, but it’s actually a top-down process where an observational error is propagated down the layers perturbing weights along the way. …


https://www.sciencephoto.com/media/776342/view/ptolemaic-system-geocentric-model-1531

Let’s begin today with the realization that Ptolemy’s model of the movement of the planets was extremely accurate. Ptolemy’s model was accurate enough to be very useful for navigators of their time. But it worked well because it was finely tuned to fit with observed experimental data.

But was wrong with Ptolemy’s model is that it did not correctly capture cause and effect. The earth and the planets revolve around the sun due to gravity and not everything revolves around the earth. This was the Copernicus model which he paid gravely for proposing.

200 years later Newton invented calculus and…


Story Telling by VQGAN & CLIP © by the guy who selected the right words to say!

If storytelling is the essence of being human then what kind of storytelling do scientists do? Scientists tell stories about the discovery of symmetries.

The strength and the flaw of human cognition is that we demand to find symmetries in our world. This is despite a reality that does not guarantee the existence of symmetries.

Man has always believed in the existence of symmetries. Human inquiry and ultimately science has always been driven by not just the discovery of some symmetries but the discovery of the ultimate symmetry.

The one symmetry to rule over all symmetries.

But by the middle…


Photo by Josh Calabrese on Unsplash

Ben Goertzel has a set of videos explaining his theory of general intelligence. It’s instructive to me to understand his framing so as to be able to compare and refine my own ideas.

Goertzel’s approach begins with a formulation of intelligence that has no resource limits (see: Hutter and Legg, AIXI). From this definition, he formulates alternatives with resource constraints.

So the model is a pragmatic specialization of a universal intelligence model. He then applies additional constraints based on cognitive architectures inspired by human intelligence.

He argues however that there can be many kinds of general intelligence that may not…

Carlos E. Perez

Author of Artificial Intuition and the Deep Learning Playbook — http://linkedin.com/in/ceperez https://twitter.com/IntuitMachine

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store